End of training

README.md

@@ -37,7 +37,7 @@ datasets:
     system_prompt: ''
 device_map: auto
 eval_sample_packing: false
-eval_steps: 200
+eval_steps: 20
 flash_attention: true
 gradient_checkpointing: true
 group_by_length: true
@@ -55,11 +55,13 @@ output_dir: /root/.sn56/axolotl/tmp/SmolLM-360M
 pad_to_sequence_len: true
 resize_token_embeddings_to_32x: false
 sample_packing: true
-save_steps: 200
+save_steps: 20
 save_total_limit: 1
 sequence_len: 2048
 tokenizer_type: GPT2TokenizerFast
 torch_dtype: bf16
+training_args_kwargs:
+  hub_private_repo: true
 trust_remote_code: true
 val_set_size: 0.1
 wandb_entity: ''
@@ -78,7 +80,7 @@ warmup_ratio: 0.05
 
 This model is a fine-tuned version of [unsloth/SmolLM-360M](https://huggingface.co/unsloth/SmolLM-360M) on the argilla/databricks-dolly-15k-curated-en dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.0617
+- Loss: 2.0673
 
 ## Model description
 
@@ -115,7 +117,16 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
 | No log        | 0.125 | 1    | 2.5584          |
-| 2.011         | 25.0  | 200  | 2.0617          |
+| 2.2406        | 2.5   | 20   | 2.1562          |
+| 2.136         | 5.0   | 40   | 2.0829          |
+| 2.0938        | 7.5   | 60   | 2.0711          |
+| 2.0632        | 10.0  | 80   | 2.0679          |
+| 2.0298        | 12.5  | 100  | 2.0621          |
+| 2.0168        | 15.0  | 120  | 2.0567          |
+| 2.0188        | 17.5  | 140  | 2.0686          |
+| 2.0108        | 20.0  | 160  | 2.0701          |
+| 2.0169        | 22.5  | 180  | 2.0683          |
+| 2.0109        | 25.0  | 200  | 2.0673          |
 
 
 ### Framework versions